Method and system for the protection of broker and investor relationships, accounts and transactions
A computer based method and system for advanced scenario based alert generation and processing is presented, with the specific ability to broker and investor activities that put either at risk. Advanced scenarios that describe such broker and investor activities are specifically defined. By applying these scenarios to transactional data from a variety of financial institutions, broker and investor activities causing unacceptable amounts of risk can be detected on an automated basis.
1. A computer program embodied on a computer executable medium for identifying a situation representing risk to a brokerage or its investors, wherein the program comprises one or more sequences of instructions that cause one or more processors to perform the steps of:
receiving data representative of:
a plurality of transactions relating to securities trading, and
a plurality of entities involved in securities trading,
wherein the plurality of transactions and the plurality of entities are not predetermined to be related:
identifying a behavior of interest comprising outlier detection analysis to identify at least one of the transactions and entities outside of a defined statistical range that are indicative of a risk to a brokerage or its investors by identifying rapid switching of a first mutual fund or a second mutual fund, wherein one or more of the plurality of transactions is a solicited transaction involving one or more customers of a securities brokerage and one or more securities representatives, wherein the solicited transaction is solicited by the securities representative, wherein proceeds associated with the switching are at least a percentage of a value of the first mutual fund;
determining whether one or more groups of the transactions and entities collectively satisfy at least one of the one or more of the sequence detection requirements;
in response to one or more groups of the transactions and entities collectively satisfying at least one of the one or more sequence detection requirements, generating an alert informing a user of the one or more groups of the transactions and entities.
2. The computer program of claim 1 , wherein the instructions further cause the one or more processors to perform one or more of the following on the plurality of transactions and the plurality of entities:
sequence matching to identify sequences in one or more transactions and to relate the identified sequences to one or more of the entities in the received data;
link analysis to establish connections between one or more transactions and entities in the received data;
rule-based analysis to identify at least one of the transactions and entities based on rules specifying parameters and thresholds;
decision tree analysis; and
detection processing using neural networks.